Related papers: Mind the Prompt: A Novel Benchmark for Prompt-base…

Large pre-trained vision-language models (VLMs) offer a promising approach to leveraging human language for enhancing downstream tasks. However, VLMs such as CLIP face significant limitation: its performance is highly sensitive to prompt…

Object counting aims to estimate the number of objects in images. The leading counting approaches focus on the single category counting task and achieve impressive performance. Note that there are multiple categories of objects in real…

Semantic segmentation is a core task in computer vision. Existing methods are generally divided into two categories: automatic and interactive. Interactive approaches, exemplified by the Segment Anything Model (SAM), have shown promise as…

Drone-captured images present significant challenges in object detection due to varying shooting conditions, which can alter object appearance and shape. Factors such as drone altitude, angle, and weather cause these variations, influencing…

Few-shot, fine-grained classification in computer vision poses significant challenges due to the need to differentiate subtle class distinctions with limited data. This paper presents a novel method that enhances the Contrastive…

Prompt tuning, a recently emerging paradigm, enables the powerful vision-language pre-training models to adapt to downstream tasks in a parameter -- and data -- efficient way, by learning the ``soft prompts'' to condition frozen…

We introduce Progressive Prompts - a simple and efficient approach for continual learning in language models. Our method allows forward transfer and resists catastrophic forgetting, without relying on data replay or a large number of…

Foundation models such as Segment Anything Model 3 (SAM3) enable flexible text-guided medical image segmentation, yet their predictions remain highly sensitive to prompt formulation. Even semantically equivalent descriptions can yield…

Class Incremental Learning (CIL) based on pre-trained models offers a promising direction for open-world continual learning. Existing methods typically rely on correlation-based strategies, where an image's classification feature is used as…

Visual explanation (attention)-guided learning uses not only labels but also explanations to guide model reasoning process. While visual attention-guided learning has shown promising results, it requires a large number of explanation…

Prompt tuning has shown promising results, but its robustness and generalization to unseen categories remain limited. Through our experiments, we demonstrate that the complete removal of semantic noise is a key factor restricting…

Class-incremental learning (CIL) enables models to learn new classes progressively while preserving knowledge of previously learned ones. Recent advances in this field have shifted towards parameter-efficient fine-tuning techniques, with…

Text-to-image diffusion models have recently become highly capable, yet their behavior in multi-object scenes remains unreliable: models often produce an incorrect number of instances and exhibit semantics leaking across objects. We trace…

Designing metrics for evaluating instance segmentation revolves around comprehensively considering object detection and segmentation accuracy. However, other important properties, such as sensitivity, continuity, and equality, are…

Multiclass classifiers are often designed and evaluated only on a sample from the classes on which they will eventually be applied. Hence, their final accuracy remains unknown. In this work we study how a classifier's performance over the…

Thanks to the large pre-trained vision-language models (VLMs) like CLIP, we can craft a zero-shot classifier by "prompt", e.g., the confidence score of an image being "[CLASS]" can be obtained by using the VLM provided similarity measure…

Contrastive Language-Image Pre-training (CLIP) represents the latest incarnation of pre-trained vision-language models. Although CLIP has recently shown its superior power on a wide range of downstream vision-language tasks like Visual…

Multi-instance Repetitive Action Counting (MRAC) aims to estimate the number of repetitive actions performed by multiple instances in untrimmed videos, commonly found in human-centric domains like sports and exercise. In this paper, we…

In this paper, we study the problem of object counting with incomplete annotations. Based on the observation that in many object counting problems the target objects are normally repeated and highly similar to each other, we are…

Significant advancements have been made in single label incremental learning (SLCIL),yet the more practical and challenging multi label class incremental learning (MLCIL) remains understudied. Recently,visual language models such as CLIP…