Search Results for author:
Found 17 papers, 5 papers with code
Harmonized Spatial and Spectral Learning for Robust and Generalized Medical Image Segmentation
This paper presents a novel approach that synergies spatial and spectral representations to enhance domain-generalized medical image segmentation.
SPEEDNet: Salient Pyramidal Enhancement Encoder-Decoder Network for Colonoscopy Images
A DIPC block combines the dilated involution layers pairwise into a pyramidal structure to convert the feature maps into a compact space.
Rethinking Intermediate Layers design in Knowledge Distillation for Kidney and Liver Tumor Segmentation
HLFD strategically distills knowledge from a combination of middle layers to earlier layers and transfers final layer knowledge to intermediate layers at both the feature and pixel levels.
SynergyNet: Bridging the Gap between Discrete and Continuous Representations for Precise Medical Image Segmentation
When evaluating skin lesion and brain tumor segmentation datasets, we observe a remarkable improvement of 1. 71% in Intersection-over Union scores for skin lesion segmentation and of 8. 58% for brain tumor segmentation.
A Survey of Techniques for Optimizing Transformer Inference
This paper presents a comprehensive survey of techniques for optimizing the inference phase of transformer networks.
GAFNet: A Global Fourier Self Attention Based Novel Network for multi-modal downstream tasks
We introduce a novel network, GAFNet (Global Attention Fourier Net), which learns through large-scale pre-training over three image-text datasets (COCO, SBU, and CC-3M), for achieving high performance on downstream vision and language tasks.
TPFNet: A Novel Text In-painting Transformer for Text Removal
Further, we use a novel multi-headed decoder that generates a high-pass filtered image and a segmentation map, in addition to a text-free image.
ACLNet: An Attention and Clustering-based Cloud Segmentation Network
We propose a novel deep learning model named ACLNet, for cloud segmentation from ground images.
Ranked #1 on
Semantic Segmentation
on SWINySEG
WaferSegClassNet -- A Light-weight Network for Classification and Segmentation of Semiconductor Wafer Defects
WSCN has a model size of only 0. 51MB and performs only 0. 2M FLOPS.
Ranked #1 on
Semantic Segmentation
on MixedWM38
Design and Analysis of Novel Bit-flip Attacks and Defense Strategies for DNNs
In this paper, we present novel bit-flip attack (BFA) algorithms for DNNs, along with techniques for defending against the attack.
Modeling Data Reuse in Deep Neural Networks by Taking Data-Types into Cognizance
arithmetic intensity, does not always correctly estimate the degree of data reuse in DNNs since it gives equal importance to all the data types.
DeepPeep: Exploiting Design Ramifications to Decipher the Architecture of Compact DNNs
The remarkable predictive performance of deep neural networks (DNNs) has led to their adoption in service domains of unprecedented scale and scope.
On the Demystification of Knowledge Distillation: A Residual Network Perspective
Surprisingly, in some cases, they surpass the accuracy of baseline networks even with the inferior teachers.
DRACO: Co-Optimizing Hardware Utilization, and Performance of DNNs on Systolic Accelerator
The number of processing elements (PEs) in a fixed-sized systolic accelerator is well matched for large and compute-bound DNNs; whereas, memory-bound DNNs suffer from PE underutilization and fail to achieve peak performance and energy efficiency.
ULSAM: Ultra-Lightweight Subspace Attention Module for Compact Convolutional Neural Networks
Our method of subspace attention is orthogonal and complementary to the existing state-of-the-arts attention mechanisms used in vision models.
The Ramifications of Making Deep Neural Networks Compact
Reducing the number of parameters in DNNs increases the number of activations which, in turn, increases the memory footprint.
E2GC: Energy-efficient Group Convolution in Deep Neural Networks
We show that, at comparable computational complexity, DNNs with constant group size (E2GC) are more energy-efficient than DNNs with a fixed number of groups (F$g$GC).
