Related papers: Adaptive Slicing-Assisted Hyper Inference for Enha…
Precision pathology relies on detecting fine-grained morphological abnormalities within specific Regions of Interest (ROIs), as these local, texture-rich cues - rather than global slide contexts - drive expert diagnostic reasoning. While…
Object detection in Unmanned Aerial Vehicle (UAV) images poses significant challenges due to complex scale variations and class imbalance among objects. Existing methods often address these challenges separately, overlooking the intricate…
We present a new pixelized method for the inversion of gravitationally lensed extended source images which we term adaptive semi-linear inversion (SLI). At the heart of the method is an h-means clustering algorithm which is used to derive a…
In object detection, data amount and cost are a trade-off, and collecting a large amount of data in a specific domain is labor intensive. Therefore, existing large-scale datasets are used for pre-training. However, conventional transfer…
Recent advances in foundation models have brought promising results in computer vision, including medical image segmentation. Fine-tuning foundation models on specific low-resource medical tasks has become a standard practice. However,…
Hashing methods have been widely used for efficient similarity retrieval on large scale image database. Traditional hashing methods learn hash functions to generate binary codes from hand-crafted features, which achieve limited accuracy…
Unsupervised hashing can desirably support scalable content-based image retrieval (SCBIR) for its appealing advantages of semantic label independence, memory and search efficiency. However, the learned hash codes are embedded with limited…
Similarity-based image hashing represents crucial technique for visual data storage reduction and expedited image search. Conventional hashing schemes typically feed hand-crafted features into hash functions, which separates the procedures…
The computational burden and inherent redundancy of large-scale datasets challenge the training of contemporary machine learning models. Data pruning offers a solution by selecting smaller, informative subsets, yet existing methods…
Existing deep learning-based hyperspectral image (HSI) classification works still suffer from the limitation of the fixed-sized receptive field, leading to difficulties in distinctive spectral-spatial features for ground objects with…
We propose an approach for unsupervised adaptation of object detectors from label-rich to label-poor domains which can significantly reduce annotation costs associated with detection. Recently, approaches that align distributions of source…
Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications. Unfortunately, it has received much less attention than supervised object detection. Models that try to address this task tend…
Recently, learning algorithms motivated from sharpness of loss surface as an effective measure of generalization gap have shown state-of-the-art performances. Nevertheless, sharpness defined in a rigid region with a fixed radius, has a…
Recently, despite the remarkable advancements in object detection, modern detectors still struggle to detect tiny objects in aerial images. One key reason is that tiny objects carry limited features that are inevitably degraded or lost…
Novel Instance Detection and Segmentation (NIDS) aims at detecting and segmenting novel object instances given a few examples of each instance. We propose a unified, simple, yet effective framework (NIDS-Net) comprising object proposal…
This paper presents a simple yet effective two-stage framework for semi-supervised medical image segmentation. Unlike prior state-of-the-art semi-supervised segmentation methods that predominantly rely on pseudo supervision directly on…
We introduce a novel video-rate hyperspectral imager with high spatial, and temporal resolutions. Our key hypothesis is that spectral profiles of pixels in a super-pixel of an oversegmented image tend to be very similar. Hence, a…
The Hierarchical Inference (HI) paradigm employs a tiered processing: the inference from simple data samples are accepted at the end device, while complex data samples are offloaded to the central servers. HI has recently emerged as an…
We present a method for performing hierarchical object detection in images guided by a deep reinforcement learning agent. The key idea is to focus on those parts of the image that contain richer information and zoom on them. We train an…
Visual place recognition algorithms trade off three key characteristics: their storage footprint, their computational requirements, and their resultant performance, often expressed in terms of recall rate. Significant prior work has…