Related papers: Revisiting AP Loss for Dense Object Detection: Ada…
We propose Rank & Sort (RS) Loss, a ranking-based loss function to train deep object detection and instance segmentation methods (i.e. visual detectors). RS Loss supervises the classifier, a sub-network of these methods, to rank each…
Adversarial examples provide an opportunity as well as impose a challenge for understanding image classification systems. Based on the analysis of the adversarial training solution Adversarial Logits Pairing (ALP), we observed in this work…
In the paradigm of object detection, the decision head is an important part, which affects detection performance significantly. Yet how to design a high-performance decision head remains to be an open issue. In this paper, we propose a…
Machine learning classification systems are susceptible to poor performance when trained with incorrect ground truth labels, even when data is well-curated by expert annotators. As machine learning becomes more widespread, it is…
High-quality data has become a primary driver of progress under scale laws, with curated datasets often outperforming much larger unfiltered ones at lower cost. Online data curation extends this idea by dynamically selecting training…
RetinaNet proposed Focal Loss for classification task and improved one-stage detectors greatly. However, there is still a gap between it and two-stage detectors. We analyze the prediction of RetinaNet and find that the misalignment of…
Accurately ranking the vast number of candidate detections is crucial for dense object detectors to achieve high performance. Prior work uses the classification score or a combination of classification and predicted localization scores to…
The 3D Average Precision (3D AP) relies on the intersection over union between predictions and ground truth objects. However, camera-only detectors have limited depth accuracy, which may cause otherwise reasonable predictions that suffer…
We propose a novel autoencoding model called Pairwise Augmented GANs. We train a generator and an encoder jointly and in an adversarial manner. The generator network learns to sample realistic objects. In turn, the encoder network at the…
Autonomous robotic systems applied to new domains require an abundance of expensive, pixel-level dense labels to train robust semantic segmentation models under full supervision. This study proposes a model-agnostic Depth Edge Alignment…
The convergence of the generalized alternating projection (GAP) algorithm is studied in this paper to solve the compressive sensing problem $\yv = \Amat \xv + \epsilonv$. By assuming that $\Amat\Amat\ts$ is invertible, we prove that GAP…
Dense retrieval has become the new paradigm in passage retrieval. Despite its effectiveness on typo-free queries, it is not robust when dealing with queries that contain typos. Current works on improving the typo-robustness of dense…
Dense retrieval (DR) has shown promising results in information retrieval. In essence, DR requires high-quality text representations to support effective search in the representation space. Recent studies have shown that pre-trained…
Coordinate descent methods employ random partial updates of decision variables in order to solve huge-scale convex optimization problems. In this work, we introduce new adaptive rules for the random selection of their updates. By adaptive,…
We study stochastic optimization with data-adaptive sampling schemes to train pairwise learning models. Pairwise learning is ubiquitous, and it covers several popular learning tasks such as ranking, metric learning and AUC maximization. A…
The ability to estimate the perceptual error between images is an important problem in computer vision with many applications. Although it has been studied extensively, however, no method currently exists that can robustly predict visual…
For object detection detectors, enhancing model performance hinges on the ability to simultaneously consider inconsistencies across tasks and focus on difficult-to-train samples. Achieving this necessitates incorporating information from…
Image Retrieval is commonly evaluated with Average Precision (AP) or Recall@k. Yet, those metrics, are limited to binary labels and do not take into account errors' severity. This paper introduces a new hierarchical AP training method for…
We revisit the problem of training attention-based sparse image matching models for various local features. We first identify one critical design choice that has been previously overlooked, which significantly impacts the performance of the…
Obtaining gold standard annotated data for object detection is often costly, involving human-level effort. Semi-supervised object detection algorithms solve the problem with a small amount of gold-standard labels and a large unlabelled…