Related papers: CASA: Class-Agnostic Shared Attributes in Vision-L…

We propose a novel framework for interactive class-agnostic object counting, where a human user can interactively provide feedback to improve the accuracy of a counter. Our framework consists of two main components: a user-friendly…

Foundation models for vision have transformed visual recognition with powerful pretrained representations and strong zero-shot capabilities, yet their potential for data-efficient learning remains largely untapped. Active Learning (AL) aims…

Multi-view action clustering leverages the complementary information from different camera views to enhance the clustering performance. Although existing approaches have achieved significant progress, they assume all camera views are…

Recent methods for long-tailed instance segmentation still struggle on rare object classes with few training data. We propose a simple yet effective method, Feature Augmentation and Sampling Adaptation (FASA), that addresses the data…

Conventional unsupervised anomaly detection (UAD) methods build separate models for each object category. Recent studies have proposed to train a unified model for multiple classes, namely model-unified UAD. However, such methods still…

Class-Incremental Learning (CIL) is important in building real-world learning systems. In CLIP-based CIL, the model performs classification by comparing similarity between visual and textual embeddings obtained from template prompts, e.g.,…

This paper explores the problem of class-agnostic anomaly detection (AD), where the objective is to train one class-agnostic AD model that can generalize to detect anomalies in diverse new classes from different domains without any…

Multi-label image recognition is a challenging computer vision task of practical use. Progresses in this area, however, are often characterized by complicated methods, heavy computations, and lack of intuitive explanations. To effectively…

Object Detection, a fundamental computer vision problem, has paramount importance in smart camera systems. However, a truly reliable camera system could be achieved if and only if the underlying object detection component is robust enough…

Unsupervised object-centric learning from videos is a promising approach towards learning compositional representations that can be applied to various downstream tasks, such as prediction and reasoning. Recently, it was shown that…

Salient object detection (SOD) is a fundamental computer vision task. Recently, with the revival of deep neural networks, SOD has made great progresses. However, there still exist two thorny issues that cannot be well addressed by existing…

Representation learning has significantly been developed with the advance of contrastive learning methods. Most of those methods have benefited from various data augmentations that are carefully designated to maintain their identities so…

In contrast to the incremental classification task, the incremental detection task is characterized by the presence of data ambiguity, as an image may have differently labeled bounding boxes across multiple continuous learning stages. This…

As few-shot object detectors are often trained with abundant base samples and fine-tuned on few-shot novel examples,the learned models are usually biased to base classes and sensitive to the variance of novel examples. To address this…

We tackle the task of Class Agnostic Counting, which aims to count objects in a novel object category at test time without any access to labeled training data for that category. All previous class agnostic counting methods cannot work in a…

Continual Learning in semantic scene segmentation aims to continually learn new unseen classes in dynamic environments while maintaining previously learned knowledge. Prior studies focused on modeling the catastrophic forgetting and…

Deep neural networks for classification are vulnerable to adversarial attacks, where small perturbations to input samples lead to incorrect predictions. This susceptibility, combined with the black-box nature of such networks, limits their…

(T)ACSA tasks, including aspect-category sentiment analysis (ACSA) and targeted aspect-category sentiment analysis (TACSA), aims at identifying sentiment polarity on predefined categories. Incremental learning on new categories is necessary…

Camouflaged Object Detection (COD) aims to segment objects that blend seamlessly into complex backgrounds, with growing interest in exploiting additional visual modalities to enhance robustness through complementary information. However,…

Temporal alignment of fine-grained human actions in videos is important for numerous applications in computer vision, robotics, and mixed reality. State-of-the-art methods directly learn image-based embedding space by leveraging powerful…