Search Results for author:
Found 43 papers, 22 papers with code
Advancing Ante-Hoc Explainable Models through Generative Adversarial Networks
This paper presents a novel concept learning framework for enhancing model interpretability and performance in visual classification tasks.
Rethinking Robustness of Model Attributions
We observe two main causes for fragile attributions: first, the existing metrics of robustness (e. g., top-k intersection) over-penalize even reasonable local shifts in attribution, thereby making random perturbations to appear as a strong attack, and second, the attribution can be concentrated in a small region even when there are multiple important parts in an image.
Causal Inference Using LLM-Guided Discovery
At the core of causal inference lies the challenge of determining reliable causal graphs solely based on observational data.
Explaining Deep Face Algorithms through Visualization: A Survey
Although current deep models for face tasks surpass human performance on some benchmarks, we do not understand how they work.
Building a Winning Team: Selecting Source Model Ensembles using a Submodular Transferability Estimation Approach
Estimating the transferability of publicly available pretrained models to a target task has assumed an important place for transfer learning tasks in recent years.
On Counterfactual Data Augmentation Under Confounding
Counterfactual data augmentation has recently emerged as a method to mitigate confounding biases in the training data.
$Δ$-Patching: A Framework for Rapid Adaptation of Pre-trained Convolutional Networks without Base Performance Loss
Models pre-trained on large-scale datasets are often fine-tuned to support newer tasks and datasets that arrive over time.
Data-Free Class-Incremental Hand Gesture Recognition
Our sampling scheme outperforms SOTA methods significantly on two 3D skeleton gesture datasets, the publicly available SHREC 2017, and EgoGesture3D -- which we extract from a publicly available RGBD dataset.
On the Robustness of Explanations of Deep Neural Network Models: A Survey
While there have been many surveys that review explainability methods themselves, there has been no effort hitherto to assimilate the different methods and metrics proposed to study the robustness of explanations of DNN models.
NESTER: An Adaptive Neurosymbolic Method for Causal Effect Estimation
Methods based on potential outcomes framework solve this problem by exploiting inductive biases and heuristics from causal inference.
Counterfactual Generation Under Confounding
Given a causal generative process, we formally characterize the adverse effects of confounding on any downstream tasks and show that the correlation between generative factors (attributes) can be used to quantitatively measure confounding between generative factors.
Distilling the Undistillable: Learning from a Nasty Teacher
The inadvertent stealing of private/sensitive information using Knowledge Distillation (KD) has been getting significant attention recently and has guided subsequent defense efforts considering its critical nature.
ARUBA: An Architecture-Agnostic Balanced Loss for Aerial Object Detection
In this paper, we denote size of an object as the number of pixels it covers in an image and size imbalance as the over-representation of certain sizes of objects in a dataset.
Novel Class Discovery without Forgetting
Inspired by this, we identify and formulate a new, pragmatic problem setting of NCDwF: Novel Class Discovery without Forgetting, which tasks a machine learning model to incrementally discover novel categories of instances from unlabeled data, while maintaining its performance on the previously seen categories.
INDIGO: Intrinsic Multimodality for Domain Generalization
To this end, we propose IntriNsic multimodality for DomaIn GeneralizatiOn (INDIGO), a simple and elegant way of leveraging the intrinsic modality present in these pre-trained multimodal networks along with the visual modality to enhance generalization to unseen domains at test-time.
Proto2Proto: Can you recognize the car, the way I do?
With growing use cases of model reuse and distillation, there is a need to also study transfer of interpretability from one model to another.
Spacing Loss for Discovering Novel Categories
Novel Class Discovery (NCD) is a learning paradigm, where a machine learning model is tasked to semantically group instances from unlabeled data, by utilizing labeled instances from a disjoint set of classes.
Unseen Classes at a Later Time? No Problem
Secondly, we introduce a unified feature-generative framework for CGZSL that leverages bi-directional incremental alignment to dynamically adapt to addition of new classes, with or without labeled data, that arrive over time in any of these CGZSL settings.
Energy-based Latent Aligner for Incremental Learning
Deep learning models tend to forget their earlier knowledge while incrementally learning new tasks.
To miss-attend is to misalign! Residual Self-Attentive Feature Alignment for Adapting Object Detectors
Qualitative results demonstrate the ability of ILLUME to attend important object instances required for alignment.
On Causally Disentangled Representations
Finally, we perform an empirical study on state of the art disentangled representation learners using our metrics and dataset to evaluate them from causal perspective.
Adversarial Robustness without Adversarial Training: A Teacher-Guided Curriculum Learning Approach
Current SOTA adversarially robust models are mostly based on adversarial training (AT) and differ only by some regularizers either at inner maximization or outer minimization steps.
Matching Learned Causal Effects of Neural Networks with Domain Priors
A trained neural network can be interpreted as a structural causal model (SCM) that provides the effect of changing input variables on the model's output.
Get Fooled for the Right Reason: Improving Adversarial Robustness through a Teacher-guided Curriculum Learning Approach
Current SOTA adversarially robust models are mostly based on adversarial training (AT) and differ only by some regularizers either at inner maximization or outer minimization steps.
Multi-Domain Incremental Learning for Semantic Segmentation
Recent efforts in multi-domain learning for semantic segmentation attempt to learn multiple geographical datasets in a universal, joint model.
A Framework for Learning Ante-hoc Explainable Models via Concepts
To the best of our knowledge, we are the first ante-hoc explanation generation method to show results with a large-scale dataset such as ImageNet.
Context-Conditional Adaptation for Recognizing Unseen Classes in Unseen Domains
Recent progress towards designing models that can generalize to unseen domains (i. e domain generalization) or unseen classes (i. e zero-shot learning) has embarked interest towards building models that can tackle both domain-shift and semantic shift simultaneously (i. e zero-shot domain generalization).
Structured Latent Embeddings for Recognizing Unseen Classes in Unseen Domains
The need to address the scarcity of task-specific annotated data has resulted in concerted efforts in recent years for specific settings such as zero-shot learning (ZSL) and domain generalization (DG), to separately address the issues of semantic shift and domain shift, respectively.
Learn from Anywhere: Rethinking Generalized Zero-Shot Learning with Limited Supervision
In this work, we present a practical setting of inductive zero and few-shot learning, where unlabeled images from other out-of-data classes, that do not belong to seen or unseen categories, can be used to improve generalization in any-shot learning.
Canonical Saliency Maps: Decoding Deep Face Models
As Deep Neural Network models for face processing tasks approach human-like performance, their deployment in critical applications such as law enforcement and access control has seen an upswing, where any failure may have far-reaching consequences.
Instance-wise Causal Feature Selection for Model Interpretation
We formulate a causal extension to the recently introduced paradigm of instance-wise feature selection to explain black-box visual classifiers.
Improving Attribution Methods by Learning Submodular Functions
This work explores the novel idea of learning a submodular scoring function to improve the specificity/selectivity of existing feature attribution methods.
Towards Open World Object Detection
Humans have a natural instinct to identify unknown object instances in their environments.
Enhanced Regularizers for Attributional Robustness
Deep neural networks are the default choice of learning models for computer vision tasks.
Data InStance Prior (DISP) in Generative Adversarial Networks
Previous works have addressed training in low data setting by leveraging transfer learning and data augmentation techniques.
A Deeper Look at the Hessian Eigenspectrum of Deep Neural Networks and its Applications to Regularization
In this work, we propose a layerwise loss landscape analysis where the loss surface at every layer is studied independently and also on how each correlates to the overall loss surface.
On Initial Pools for Deep Active Learning
While recent studies have focused on evaluating the robustness of various query functions in AL, little to no attention has been given to the design of the initial labeled pool for deep active learning.
Beyond VQA: Generating Multi-word Answer and Rationale to Visual Questions
To take this a step forward, we introduce a new task: ViQAR (Visual Question Answering and Reasoning), wherein a model must generate the complete answer and a rationale that seeks to justify the generated answer.
Evaluating and Mitigating Bias in Image Classifiers: A Causal Perspective Using Counterfactuals
We present a method for generating counterfactuals by incorporating a structural causal model (SCM) in an improved variant of Adversarially Learned Inference (ALI), that generates counterfactuals in accordance with the causal relationships between attributes of an image.
On Adversarial Robustness: A Neural Architecture Search perspective
We show that NAS, which is popular for achieving SoTA accuracy, can provide adversarial accuracy as a free add-on without any form of adversarial training.
Universalization of any adversarial attack using very few test examples
For VGG16 and VGG19 models trained on ImageNet, our simple universalization of Gradient, FGSM, and DeepFool perturbations using a test sample of 64 images gives fooling rates comparable to state-of-the-art universal attacks \cite{Dezfooli17, Khrulkov18} for reasonable norms of perturbation.
Incremental Object Detection via Meta-Learning
In a real-world setting, object instances from new classes can be continuously encountered by object detectors.
Can we have it all? On the Trade-off between Spatial and Adversarial Robustness of Neural Networks
(Non-)robustness of neural networks to small, adversarial pixel-wise perturbations, and as more recently shown, to even random spatial transformations (e. g., translations, rotations) entreats both theoretical and empirical understanding.
