Novel Object Detection
21 papers with code • 1 benchmarks • 1 datasets
Novel Object Detection is a challenging task introduced by Fomenko et.al. in their paper "Learning to Discover and Detect Objects". The goal in this task is to measure mAP performance on known as well as novel classes, where the known classes correspond to the 80 COCO classes, and the novel classes are the remaining 1123 classes from LVIS dataset. Thus, during training the model can only be trained with annotations from COCO dataset, but during evaluation/inference it is expected to BOTH classify and detect objects belonging to ALL the classes in the LVIS dataset.
Benchmarks
These leaderboards are used to track progress in Novel Object Detection
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
LVIS
Most implemented papers
SaRNet: A Dataset for Deep Learning Assisted Search and Rescue with Satellite Imagery
Access to high resolution satellite imagery has dramatically increased in recent years as several new constellations have entered service.
A Unified Objective for Novel Class Discovery
DonkeyShot21/UNO
•
•
ICCV 2021
In this paper, we study the problem of Novel Class Discovery (NCD).
CvT-ASSD: Convolutional vision-Transformer Based Attentive Single Shot MultiBox Detector
Due to the success of Bidirectional Encoder Representations from Transformers (BERT) in natural language process (NLP), the multi-head attention transformer has been more and more prevalent in computer-vision researches (CV).
Scaling Novel Object Detection with Weakly Supervised Detection Transformers
tmlabonte/weakly-supervised-DETR
•
•
A critical object detection task is finetuning an existing model to detect novel objects, but the standard workflow requires bounding box annotations which are time-consuming and expensive to collect.
Learning to Discover and Detect Objects
vlfom/rncdl
•
•
We then train our network to learn to classify each RoI, either as one of the known classes, seen in the source dataset, or one of the novel classes, with a long-tail distribution constraint on the class assignments, reflecting the natural frequency of classes in the real world.
DesCo: Learning Object Recognition with Rich Language Descriptions
liunian-harold-li/desco
•
•
NeurIPS 2023
In fact, our experiments show that GLIP, the state-of-the-art vision-language model for object detection, often disregards contextual information in the language descriptions and instead relies heavily on detecting objects solely by their names.
DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection
We refer to this approach as the self-training strategy, which enhances recall and accuracy for novel classes without requiring extra annotations, datasets, and re-training.
Beyond the Benchmark: Detecting Diverse Anomalies in Videos
yoavarad/mfad
•
•
MFAD excels in both simple and complex anomaly detection scenarios.
Enhancing Novel Object Detection via Cooperative Foundational Models
rohit901/cooperative-foundational-models
•
•
We present a novel approach to transform existing closed-set detectors into open-set detectors.
Fine-Grained Prototypes Distillation for Few-Shot Object Detection
wangchen1801/fpd
•
•
However, the class-level prototypes are difficult to precisely generate, and they also lack detailed information, leading to instability in performance. New methods are required to capture the distinctive local context for more robust novel object detection.
