Related papers: Hierarchical Compact Clustering Attention (COCA) f…

Unsupervised object-centric learning methods allow the partitioning of scenes into entities without additional localization information and are excellent candidates for reducing the annotation burden of multiple-object tracking (MOT)…

Deep learning has shown state-of-art classification performance on datasets such as ImageNet, which contain a single object in each image. However, multi-object classification is far more challenging. We present a unified framework which…

Without using extra 3-D data like points cloud or depth images for providing 3-D information, we retrieve the 3-D object information from single monocular images. The high-quality predicted depth images are recovered from single monocular…

Multimodal learning has gained much success in recent years. However, current multimodal fusion methods adopt the attention mechanism of Transformers to implicitly learn the underlying correlation of multimodal features. As a result, the…

Learning discriminative representations for subtle localized details plays a significant role in Fine-grained Visual Categorization (FGVC). Compared to previous attention-based works, our work does not explicitly define or localize the part…

Non-Local Attention (NLA) is a powerful technique for capturing long-range feature correlations in deep single image super-resolution (SR). However, NLA suffers from high computational complexity and memory consumption, as it requires…

Object counting has achieved remarkable success on visible instances, yet state-of-the-art (SOTA) methods fail under occlusion. This failure stems from a fundamental architectural limitation where backbone networks encode occluding surfaces…

Object co-segmentation is to segment the shared objects in multiple relevant images, which has numerous applications in computer vision. This paper presents a spatial and semantic modulated deep network framework for object co-segmentation.…

Object-based attention is a key component of the visual system, relevant for perception, learning, and memory. Neurons tuned to features of attended objects tend to be more active than those associated with non-attended objects. There is a…

The objective of this paper is a model that is able to discover, track and segment multiple moving objects in a video. We make four contributions: First, we introduce an object-centric segmentation model with a depth-ordered layer…

We introduce Cluster Contrast (CueCo), a novel approach to unsupervised visual representation learning that effectively combines the strengths of contrastive learning and clustering methods. Inspired by recent advancements, CueCo is…

Capsule Networks have shown tremendous advancement in the past decade, outperforming the traditional CNNs in various task due to it's equivariant properties. With the use of vector I/O which provides information of both magnitude and…

Accurately representing the complex linkages and inherent uncertainties included in huge datasets is still a major difficulty in the field of data clustering. We address these issues with our proposed Unified Neutrosophic Clustering…

Camouflaged object detection (COD) remains a challenging task in computer vision. Existing methods often resort to additional branches for edge supervision, incurring substantial computational costs. To address this, we propose the…

Object recognition in the presence of background clutter and distractors is a central problem both in neuroscience and in machine learning. However, the performance level of the models that are inspired by cortical mechanisms, including…

We consider the problem of referring camouflaged object detection (Ref-COD), a new task that aims to segment specified camouflaged objects based on a small set of referring images with salient target objects. We first assemble a large-scale…

After learning a new object category from image-level annotations (with no object bounding boxes), humans are remarkably good at precisely localizing those objects. However, building good object localizers (i.e., detectors) currently…

Contextual information provides important cues for disambiguating visually similar pixels in scene segmentation. In this paper, we introduce a neuron-level Selective Context Aggregation (SCA) module for scene segmentation, comprised of a…

Segmenting highly-overlapping objects is challenging, because typically no distinction is made between real object contours and occlusion boundaries. Unlike previous two-stage instance segmentation methods, we model image formation as…

Object-centric representations form the basis of human perception, and enable us to reason about the world and to systematically generalize to new settings. Currently, most works on unsupervised object discovery focus on slot-based…