F-CAM: Full Resolution CAM via Guided Parametric Upscaling | Semantic Scholar (2025)

High uncertainty is introduced as a criterion to localize non-discriminative regions that do not affect classifier decision, and is described with original Kullback-Leibler (KL) divergence losses evaluating the deviation of posterior predictions from the uniform distribution.

Going from single-shot detectors that require bounding box annotations of each person in an image, to auto-encoders that only rely on unlabelled images that do not contain people, allows for considerable savings in terms of annotation costs, and for models with lower computational costs.

This paper proposes a simple yet efficient method called NEGEV, which benefits from the fully negative samples that naturally occur in the data, without any additional supervision signals beyond image-class labels, to reduce false positives/negatives.

This paper introduces an enhanced visual explanation in terms of visual sharpness called SS-CAM, which produces centralized localization of object features within an image through a smooth operation, which outperforms Score-C CAM on both faithfulness and localization tasks.

It is argued that WSOL task is ill-posed with only image-level labels, and a new evaluation protocol is proposed where full supervision is limited to only a small held-out set not overlapping with the test set.

Self-produced Guidance (SPG) masks which separate the foreground i.e., the object of interest, from the background to provide the classification networks with spatial correlation information of pixels are proposed.

The integration operation within the Score-CAM pipeline is introduced, where it is introduced to achieve visually sharper attribution maps quantitatively to make CNNs more interpretable and trustworthy.

This paper proposes a simple but effective Shallow feature-aware Pseudo supervised Object Localization (SPOL) model for accurate WSOL, which makes the utmost of low-level features embedded in shallow layers and proposes a general class-agnostic segmentation model to achieve the accurate object mask.

This paper systematically explores in simulation the design space of deep interactive segmentation models and reports new insights and caveats, and presents a technique for automatically estimating the quality of the produced masks which exploits indirect signals from the annotation process.

This work proposes a two-stage approach to generate the localization maps by simply comparing the similarity of point-wise features between the high-activation and the rest pixels and introduces a novel self-enhancement method to harvest accurate object localization maps and object boundaries with only category labels as supervision.

A convolutional, multi-scale spatial localization network that provides accurate localization for the object of interest and experimental results show that the proposed approach provides competitive performance for weakly supervised localization.

The Smooth Grad-CAM++ technique provides the capability of either visualizing a layer, subset of feature maps, or subset of neurons within a feature map at each instance at the inference level (model prediction process).

This paper introduces two axioms -- Conservation and Sensitivity -- to the visualization paradigm of the CAM methods and proposes a dedicated Axiom-based Grad-CAM (XGrad-Cam) that is able to achieve better visualization performance and be class-discriminative and easy-to-implement compared with Grad-cAM++ and Ablation-C AM.

...

...