Related papers: DiSa: Saliency-Aware Foreground-Background Disenta…
Recent CLIP-like Vision-Language Models (VLMs), pre-trained on large amounts of image-text pairs to align both modalities with a simple contrastive objective, have paved the way to open-vocabulary semantic segmentation. Given an arbitrary…
Open vocabulary image segmentation tackles the challenge of recognizing dynamically adjustable, predefined novel categories at inference time by leveraging vision-language alignment. However, existing paradigms typically perform…
Research works on the two topics of Semantic Segmentation and SLAM (Simultaneous Localization and Mapping) have been following separate tracks. Here, we link them quite tightly by delineating a category label fusion technique that allows…
While fine-tuning pre-trained networks has become a popular way to train image segmentation models, such backbone networks for image segmentation are frequently pre-trained using image classification source datasets, e.g., ImageNet. Though…
Despite their effectiveness in a wide range of tasks, deep architectures suffer from some important limitations. In particular, they are vulnerable to catastrophic forgetting, i.e. they perform poorly when they are required to update their…
From video, we reconstruct a neural volume that captures time-varying color, density, scene flow, semantics, and attention information. The semantics and attention let us identify salient foreground objects separately from the background…
The open-vocabulary image segmentation task involves partitioning images into semantically meaningful segments and classifying them with flexible text-defined categories. The recent vision-based foundation models such as the Segment…
Open-vocabulary semantic segmentation (OVSS) conducts pixel-level classification via text-driven alignment, where the domain discrepancy between base category training and open-vocabulary inference poses challenges in discriminative…
Open-Set Domain Adaptation (OSDA) confronts the dual challenge of aligning known-class distributions across domains while identifying target-domain-specific unknown categories. Current approaches often fail to leverage semantic…
Despite significant progress in Unified Multimodal Retrieval (UMR) powered by Large Multimodal Models (LMMs), existing embedding methods primarily focus on sample-level objectives via contrastive learning while overlooking the crucial…
Recently, test-time adaptation has attracted wide interest in the context of vision-language models for image classification. However, to the best of our knowledge, the problem is completely overlooked in dense prediction tasks such as…
Interpreting complex deep networks, notably pre-trained vision-language models (VLMs), is a formidable challenge. Current Class Activation Map (CAM) methods highlight regions revealing the model's decision-making basis but lack clear…
Open-vocabulary semantic segmentation (OVSS) is fundamentally hampered by the coarse, image-level representations of CLIP, which lack precise pixel-level details. Existing training-free methods attempt to resolve this by either importing…
We propose a novel algorithm for weakly supervised semantic segmentation based on image-level class labels only. In weakly supervised setting, it is commonly observed that trained model overly focuses on discriminative parts rather than the…
We present lazy visual grounding, a two-stage approach of unsupervised object mask discovery followed by object grounding, for open-vocabulary semantic segmentation. Plenty of the previous art casts this task as pixel-to-text classification…
Weakly Supervised Semantic Segmentation (WSSS) with image-level labels aims to achieve pixel-level predictions using Class Activation Maps (CAMs). Recently, Contrastive Language-Image Pre-training (CLIP) has been introduced in WSSS.…
Deep neural network-based semantic segmentation generally requires large-scale cost extensive annotations for training to obtain better performance. To avoid pixel-wise segmentation annotations which are needed for most methods, recently…
Open-vocabulary semantic segmentation strives to distinguish pixels into different semantic groups from an open set of categories. Most existing methods explore utilizing pre-trained vision-language models, in which the key is to adopt the…
Few-shot learning (FSL) aims to generalize to novel categories with only a few samples. Recent approaches incorporate large language models (LLMs) to enrich visual representations with semantic embeddings derived from class names. However,…
Segmentation is the assigning of a semantic class to every pixel in an image and is a prerequisite for various statistical analysis tasks in materials science, like phase quantification, physics simulations or morphological…