Feature Pyramid Networks (FPN) Explained
Learn how Feature Pyramid Networks build multi-scale feature representations through top-down pathways and lateral connections for robust object detection.
Explore machine learning concepts related to Computer Vision. Clear explanations and practical insights.
Learn how Feature Pyramid Networks build multi-scale feature representations through top-down pathways and lateral connections for robust object detection.
Understanding region-based feature extraction for object detection, from quantized pooling to sub-pixel alignment and adaptive sampling
Compare anchor-based vs anchor-free object detection: Faster R-CNN and RetinaNet anchors vs FCOS and CenterNet point-based methods.
Understanding how neural architecture search discovers optimal feature pyramid architectures that outperform hand-designed alternatives
Understanding end-to-end object detection with transformers, from DETR's object queries to bipartite matching and attention-based localization
Interactive guide to convolution in CNNs: visualize sliding windows, kernels, stride, padding, and feature detection with step-by-step demos.
Understanding Non-Maximum Suppression algorithms for object detection post-processing, from greedy NMS to soft variants
Compare edge, frequency and entropy heuristics for selecting a fixed budget of image patches, and distinguish token counts from accuracy and measured speed.
Read an image as an array: inspect RGB channels, grayscale and HSV, and understand coordinates, data types and tensor layouts before preprocessing.
Understand receptive fields in CNNs: how convolutional layers expand their field of view and the gap between theoretical and effective receptive fields.
Compare nearest-neighbor and bilinear image resizing, see aliasing when downsampling, and understand aspect ratio, letterboxing and mask interpolation.
Inspect Gaussian smoothing and Sobel filters as local weighted sums, understand signed gradients and Canny edges, and connect fixed filters to CNNs.
Follow an image through convolution, ReLU, pooling and class scores. Inspect a transparent toy CNN and learn what classification can and cannot predict.
Convert between xyxy, xywh and center-size boxes, normalize coordinates correctly, and avoid mistakes when resizing, clipping or flipping detection labels.
Understand object detection from image features to boxes, classes and scores. Compare one-stage and two-stage pipelines, training and duplicate handling.
Calculate box intersection and union, explore how position and size change IoU, and distinguish overlap used for evaluation, NMS and localization losses.
Match detections to objects, inspect precision–recall curves, calculate average precision, and distinguish confidence thresholds from IoU thresholds.
Compare semantic, instance and panoptic label maps, inspect individual pixels, and understand dense predictions, mask IoU, Dice and boundary errors.
Transform images and annotations together, inspect crop and flip geometry, and choose augmentation assumptions that preserve the meaning of the task.
Follow pixels into image features, compare spatial maps with pooled vectors, and see why image encoders expose different outputs for recognition and localization.
Turn an image into a sequence: count patches, flatten pixels, apply a shared learned projection, and separate token count from embedding width.
Follow spatial image features into DETR decoder slots, separating learned query embeddings, attention queries, changing content and object predictions.
Learn how DETR assigns unordered object targets to prediction slots, why greedy choices can fail, and how matching differs from training loss and evaluation.
Learn how normalized box coordinates, L1 loss, IoU, and Generalized IoU guide object localization, including disjoint boxes and containment limits.
Learn visual complexity analysis in deep learning - how neural networks measure entropy, edges, and saliency for adaptive image processing.
Evaluate frozen image features with nearest neighbors and linear probes, separate training from validation and test data, and understand what each protocol can establish.
Follow coarse feature maps into aligned pixel predictions: nearest and bilinear interpolation, transposed convolution, output shapes, skip fusion, and resizing logits before selecting labels.
Follow a query from a spatial reference through learned offsets, bilinear feature sampling and weighted aggregation, with exact non-square coordinate arithmetic.
Follow a 3D world point through camera extrinsics, depth division and pixel intrinsics, then see why one image point cannot determine its depth.
Follow image points between frames, distinguish forward flow from backward sampling, and understand brightness constancy, occlusion and the aperture problem.
Move a pretrained encoder to a downstream task: trace frozen features, head training, partial and full fine-tuning, learning rates, and BatchNorm state.